{"ID":2871061,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12176","arxiv_id":"2509.12176","title":"From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learning","abstract":"Human face synthesis and manipulation are increasingly important in entertainment and AI, with a growing demand for highly realistic, identity-preserving images even when only unpaired, unaligned datasets are available. We study unpaired face manipulation via adversarial learning, moving from autoencoder baselines to a robust, guided CycleGAN framework. While autoencoders capture coarse identity, they often miss fine details. Our approach integrates spectral normalization for stable training, identity- and perceptual-guided losses to preserve subject identity and high-level structure, and landmark-weighted cycle constraints to maintain facial geometry across pose and illumination changes. Experiments show that our adversarial trained CycleGAN improves realism (FID), perceptual quality (LPIPS), and identity preservation (ID-Sim) over autoencoders, with competitive cycle-reconstruction SSIM and practical inference times, which achieved high quality without paired datasets and approaching pix2pix on curated paired subsets. These results demonstrate that guided, spectrally normalized CycleGANs provide a practical path from autoencoders to robust unpaired face manipulation.","short_abstract":"Human face synthesis and manipulation are increasingly important in entertainment and AI, with a growing demand for highly realistic, identity-preserving images even when only unpaired, unaligned datasets are available. We study unpaired face manipulation via adversarial learning, moving from autoencoder baselines to a...","url_abs":"https://arxiv.org/abs/2509.12176","url_pdf":"https://arxiv.org/pdf/2509.12176v2","authors":"[\"Collin Guo\",\"Yi Qian\"]","published":"2025-09-15T17:40:19Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}